The Agent Skills Directory

[NO_CODE]: The skill consists entirely of natural language instructions and does not include any scripts, executable code, or external software dependencies.
[PROMPT_INJECTION]: The skill is designed to process paper metadata, which presents a surface for indirect prompt injection. However, this is inherent to its primary purpose and is documented as a safety consideration rather than a malicious finding.
Ingestion points: Scans .md files in $OBSIDIAN_VAULT/papers/ to read YAML frontmatter.
Boundary markers: No specific boundary markers or instructions to ignore embedded content are used when reading note metadata.
Capability inventory: Access to read and write within the local Obsidian vault directory.
Sanitization: No explicit sanitization of input metadata is described before updating the index file.
[SAFE]: There are no indicators of credential theft, remote code execution, or unauthorized network communication.

paper-index